System is built on top of the System Platform, which comprises a suite of models, APIs, connectors, and packages powered by a large-scale graph database.
The platform extracts, enriches, normalizes, resolves and stores metadata about things that are related statistically. These relationships can be searched and retrieved through open standards. The essence of the platform is the statistical relationship.
Statistical and other metadata retrieval from various primary sources using Large Language Models (LLMs) and other methods.
Algorithms to compute various additional statistical metadata.
Algorithms to detect and determine strength and significance of statistical associations.
Entity resolution to match objects semantically
Large-scale graph database
Graph traversal to gather statistically related objects
APIs to present the system of an object
The platform is designed based on our values and charter commitments, and our first principles. These principles include:
Retrieve and encode relationships at the highest possible resolution to preserve fidelity.
Be as objective, impartial, precise, and transparent as possible in how we represent information.
Edge-first. Design schemas from the edge out.
Integrate seamlessly with other parts of the data stack and the infrastructure of open knowledge.
Maximize node reusability and reuse to map the world as one system.
Minimize user data storage and personal data use.
We are always investigating ways to make the platform more open and interoperable.
At System, we believe that it is time to evolve the way we organize data and knowledge: from silos to systems. So starting from first principles we invented and patented a new way of organizing and discovering information — based primarily on measured statistical relationships between things in the world.